
Independent company · San Francisco, United States
Canopy Labs
A speech AI lab behind Orpheus, a family of Llama-based text-to-speech models released in March 2025 for open use.
San Francisco, United States
- Founded
- 2024
- Type
- Independent company
- Based in
- San Francisco, United States
- Featured projects
- 3
About
Canopy Labs released Orpheus in March 2025, a text-to-speech system built on a Llama 3B backbone, with models published on GitHub and Hugging Face.
The family is available in sizes from 150M to 3B parameters. Sources disagree on the exact weight licence, so users should check the repository. The lab has not published a public team page.
Mission and ambitionsThe lab develops expressive, low-latency speech models.
Known for
- 01
Orpheus TTS
- 02
Emotion-tagged speech synthesis
Milestones
- 2025
Orpheus released
A Llama-based TTS family released as open source.
Open source
Towards human-sounding speech
- orpheus-3b-0.1-ftmodel
Fine-tuned Orpheus 3B
Pretrained Orpheus 3B
Notable releases
Openness
Apache-2.0 Orpheus code and weights.
Contact and community
Via website.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



